© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55480
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and mathematical methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aryl
    -0.07
     barg
    -0.06
    ullen
    -0.06
    lify
    -0.06
    reme
    -0.06
     cust
    -0.06
    idot
    -0.06
    cust
    -0.06
    longleftrightarrow
    -0.06
    oe
    -0.06
    POSITIVE LOGITS
    andid
    0.07
     Motion
    0.07
    éĽħ
    0.07
     trous
    0.06
    ImageData
    0.06
    ingham
    0.06
    æŃ
    0.06
    ICI
    0.06
    ackers
    0.06
    stral
    0.06
    Activations Density 0.043%

    No Known Activations